INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

##

-0.31

critical

-0.29

–

-0.27

chal

-0.27

ä»ĸåľ¨

-0.27

è´´

-0.27

ä½Ļ

-0.26

ail

-0.26

éĤ£å°±æĺ¯

-0.25

POSITIVE LOGITS

è¾ĥå¥½

0.31

åŀ©

0.27

 radiation

0.26

iste

0.25

è¾ĥå¤§

0.25

èµĦ

0.25

Radi

0.24

VICE

0.24

/preferences

0.24

_rf

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.